TSTP Solution File: PUZ081^3 by Vampire-SAT---4.8

View Problem - Process Solution

%------------------------------------------------------------------------------
% File     : Vampire-SAT---4.8
% Problem  : PUZ081^3 : TPTP v8.1.2. Released v3.6.0.
% Transfm  : none
% Format   : tptp:raw
% Command  : vampire --mode casc_sat -m 16384 --cores 7 -t %d %s

% Computer : n017.cluster.edu
% Model    : x86_64 x86_64
% CPU      : Intel(R) Xeon(R) CPU E5-2620 v4 2.10GHz
% Memory   : 8042.1875MB
% OS       : Linux 3.10.0-693.el7.x86_64
% CPULimit : 300s
% WCLimit  : 300s
% DateTime : Sun May  5 08:50:31 EDT 2024

% Result   : Theorem 0.22s 0.38s
% Output   : Refutation 0.22s
% Verified : 
% SZS Type : -

% Comments : 
%------------------------------------------------------------------------------
%----WARNING: Could not form TPTP format derivation
%------------------------------------------------------------------------------
%----ORIGINAL SYSTEM OUTPUT
% 0.03/0.12  % Problem    : PUZ081^3 : TPTP v8.1.2. Released v3.6.0.
% 0.13/0.14  % Command    : vampire --mode casc_sat -m 16384 --cores 7 -t %d %s
% 0.14/0.35  % Computer : n017.cluster.edu
% 0.14/0.35  % Model    : x86_64 x86_64
% 0.14/0.35  % CPU      : Intel(R) Xeon(R) CPU E5-2620 v4 @ 2.10GHz
% 0.14/0.35  % Memory   : 8042.1875MB
% 0.14/0.35  % OS       : Linux 3.10.0-693.el7.x86_64
% 0.14/0.35  % CPULimit   : 300
% 0.14/0.35  % WCLimit    : 300
% 0.14/0.35  % DateTime   : Fri May  3 18:10:23 EDT 2024
% 0.22/0.35  % CPUTime    : 
% 0.22/0.36  % (30605)Running in auto input_syntax mode. Trying TPTP
% 0.22/0.37  % (30608)fmb+10_1_bce=on:fmbas=expand:fmbksg=on:fmbsr=1.3_569 on theBenchmark for (569ds/0Mi)
% 0.22/0.37  % (30611)dis+1_20_av=off:lcm=predicate:nm=2:nwc=2.0_396 on theBenchmark for (396ds/0Mi)
% 0.22/0.37  % (30607)fmb+10_1_fmbas=off:fmbsr=1.3:nm=2_1451 on theBenchmark for (1451ds/0Mi)
% 0.22/0.37  % (30610)fmb+10_1_bce=on:fmbas=expand:fmbksg=on:fmbsr=1.3:gsp=on:nm=4_470 on theBenchmark for (470ds/0Mi)
% 0.22/0.37  % (30613)fmb+10_1_fmbas=off:fmbsr=1.3:nm=2:si=on:rtra=on:rawr=on:rp=on:fmbksg=on_1451 on theBenchmark for (1451ds/0Mi)
% 0.22/0.37  % (30609)dis-2_2:3_amm=sco:anc=none:bce=on:fsr=off:gsp=on:nm=16:nwc=1.2:nicw=on:sac=on:sp=weighted_frequency_476 on theBenchmark for (476ds/0Mi)
% 0.22/0.37  % (30612)dis+11_4:5_nm=4_216 on theBenchmark for (216ds/0Mi)
% 0.22/0.37  % (30610)WARNING: Not using GeneralSplitting currently not compatible with polymorphic/higher-order inputs.
% 0.22/0.37  % Exception at run slice level
% 0.22/0.37  User error: Finite model buillding is currently not compatible with polymorphism or higher-order constructs
% 0.22/0.37  % Exception at run slice level
% 0.22/0.37  User error: Finite model buillding is currently not compatible with polymorphism or higher-order constructs
% 0.22/0.37  % Exception at run slice level
% 0.22/0.37  % (30609)WARNING: Not using GeneralSplitting currently not compatible with polymorphic/higher-order inputs.
% 0.22/0.37  User error: Finite model buillding is currently not compatible with polymorphism or higher-order constructs
% 0.22/0.38  % Exception at run slice level
% 0.22/0.38  User error: Finite model buillding is currently not compatible with polymorphism or higher-order constructs
% 0.22/0.38  % (30609)First to succeed.
% 0.22/0.38  % (30611)Also succeeded, but the first one will report.
% 0.22/0.38  % (30609)Solution written to "/export/starexec/sandbox/tmp/vampire-proof-30605"
% 0.22/0.38  % (30612)Also succeeded, but the first one will report.
% 0.22/0.38  % (30609)Refutation found. Thanks to Tanya!
% 0.22/0.38  % SZS status Theorem for theBenchmark
% 0.22/0.38  % SZS output start Proof for theBenchmark
% 0.22/0.38  thf(type_def_5, type, sTfun: ($tType * $tType) > $tType).
% 0.22/0.38  thf(func_def_2, type, knight: $i > $o).
% 0.22/0.38  thf(func_def_3, type, knave: $i > $o).
% 0.22/0.38  thf(func_def_4, type, says: $i > $o > $o).
% 0.22/0.38  thf(func_def_8, type, vAND: $o > $o > $o).
% 0.22/0.38  thf(func_def_9, type, vNOT: $o > $o).
% 0.22/0.38  thf(func_def_11, type, kCOMB: !>[X0: $tType, X1: $tType]:(X0 > X1 > X0)).
% 0.22/0.38  thf(func_def_12, type, bCOMB: !>[X0: $tType, X1: $tType, X2: $tType]:((X1 > X2) > (X0 > X1) > X0 > X2)).
% 0.22/0.38  thf(func_def_13, type, vOR: $o > $o > $o).
% 0.22/0.38  thf(func_def_14, type, vIMP: $o > $o > $o).
% 0.22/0.38  thf(func_def_15, type, vEQ: !>[X0: $tType]:(X0 > X0 > $o)).
% 0.22/0.38  thf(f115,plain,(
% 0.22/0.38    $false),
% 0.22/0.38    inference(avatar_sat_refutation,[],[f71,f87,f111])).
% 0.22/0.38  thf(f111,plain,(
% 0.22/0.38    ~spl0_1),
% 0.22/0.38    inference(avatar_contradiction_clause,[],[f110])).
% 0.22/0.38  thf(f110,plain,(
% 0.22/0.38    $false | ~spl0_1),
% 0.22/0.38    inference(trivial_inequality_removal,[],[f104])).
% 0.22/0.38  thf(f104,plain,(
% 0.22/0.38    ($true != $true) | ~spl0_1),
% 0.22/0.38    inference(superposition,[],[f102,f96])).
% 0.22/0.38  thf(f96,plain,(
% 0.22/0.38    ($true = vAPP($o,$o,vAPP($i,sTfun($o,$o),says,zoey),$true)) | ~spl0_1),
% 0.22/0.38    inference(backward_demodulation,[],[f32,f94])).
% 0.22/0.38  thf(f94,plain,(
% 0.22/0.38    ( ! [X0 : $i] : ((vAPP($i,$o,knave,X0) = $true)) ) | ~spl0_1),
% 0.22/0.38    inference(trivial_inequality_removal,[],[f93])).
% 0.22/0.38  thf(f93,plain,(
% 0.22/0.38    ( ! [X0 : $i] : (($true = $false) | (vAPP($i,$o,knave,X0) = $true)) ) | ~spl0_1),
% 0.22/0.38    inference(forward_demodulation,[],[f35,f89])).
% 0.22/0.38  thf(f89,plain,(
% 0.22/0.38    ( ! [X0 : $i] : ((vAPP($i,$o,knight,X0) = $false)) ) | ~spl0_1),
% 0.22/0.38    inference(trivial_inequality_removal,[],[f88])).
% 0.22/0.38  thf(f88,plain,(
% 0.22/0.38    ( ! [X0 : $i] : (($true != $true) | (vAPP($i,$o,knight,X0) = $false)) ) | ~spl0_1),
% 0.22/0.38    inference(superposition,[],[f67,f9])).
% 0.22/0.38  thf(f9,plain,(
% 0.22/0.38    ( ! [X0 : $o] : (($true = X0) | ($false = X0)) )),
% 0.22/0.38    introduced(fool_axiom,[])).
% 0.22/0.38  thf(f67,plain,(
% 0.22/0.38    ( ! [X0 : $i] : ((vAPP($i,$o,knight,X0) != $true)) ) | ~spl0_1),
% 0.22/0.38    inference(avatar_component_clause,[],[f66])).
% 0.22/0.38  thf(f66,plain,(
% 0.22/0.38    spl0_1 <=> ! [X0] : (vAPP($i,$o,knight,X0) != $true)),
% 0.22/0.38    introduced(avatar_definition,[new_symbols(naming,[spl0_1])])).
% 0.22/0.38  thf(f35,plain,(
% 0.22/0.38    ( ! [X0 : $i] : ((vAPP($i,$o,knight,X0) = $true) | (vAPP($i,$o,knave,X0) = $true)) )),
% 0.22/0.38    inference(binary_proxy_clausification,[],[f29])).
% 0.22/0.38  thf(f29,plain,(
% 0.22/0.38    ( ! [X0 : $i] : ((vAPP($i,$o,knight,X0) != vAPP($i,$o,knave,X0))) )),
% 0.22/0.38    inference(cnf_transformation,[],[f13])).
% 0.22/0.38  thf(f13,plain,(
% 0.22/0.38    ! [X0] : (vAPP($i,$o,knight,X0) != vAPP($i,$o,knave,X0))),
% 0.22/0.38    inference(fool_elimination,[],[f12])).
% 0.22/0.38  thf(f12,plain,(
% 0.22/0.38    ! [X0] : (vAPP($i,$o,knight,X0) <~> vAPP($i,$o,knave,X0))),
% 0.22/0.38    inference(rectify,[],[f1])).
% 0.22/0.38  thf(f1,axiom,(
% 0.22/0.38    ! [X0] : (vAPP($i,$o,knight,X0) <~> vAPP($i,$o,knave,X0))),
% 0.22/0.38    file('/export/starexec/sandbox/benchmark/theBenchmark.p',knights_xor_knaves)).
% 0.22/0.38  thf(f32,plain,(
% 0.22/0.38    (vAPP($o,$o,vAPP($i,sTfun($o,$o),says,zoey),vAPP($i,$o,knave,mel)) = $true)),
% 0.22/0.38    inference(cnf_transformation,[],[f19])).
% 0.22/0.38  thf(f19,plain,(
% 0.22/0.38    (vAPP($o,$o,vAPP($i,sTfun($o,$o),says,zoey),vAPP($i,$o,knave,mel)) = $true)),
% 0.22/0.38    inference(fool_elimination,[],[f18])).
% 0.22/0.38  thf(f18,plain,(
% 0.22/0.38    vAPP($o,$o,vAPP($i,sTfun($o,$o),says,zoey),vAPP($i,$o,knave,mel))),
% 0.22/0.38    inference(rectify,[],[f4])).
% 0.22/0.38  thf(f4,axiom,(
% 0.22/0.38    vAPP($o,$o,vAPP($i,sTfun($o,$o),says,zoey),vAPP($i,$o,knave,mel))),
% 0.22/0.38    file('/export/starexec/sandbox/benchmark/theBenchmark.p',zoey_speaks)).
% 0.22/0.38  thf(f102,plain,(
% 0.22/0.38    ( ! [X0 : $i] : (($true != vAPP($o,$o,vAPP($i,sTfun($o,$o),says,X0),$true))) ) | ~spl0_1),
% 0.22/0.38    inference(trivial_inequality_removal,[],[f101])).
% 0.22/0.38  thf(f101,plain,(
% 0.22/0.38    ( ! [X0 : $i] : (($true != $true) | ($true != vAPP($o,$o,vAPP($i,sTfun($o,$o),says,X0),$true))) ) | ~spl0_1),
% 0.22/0.38    inference(forward_demodulation,[],[f34,f94])).
% 0.22/0.38  thf(f34,plain,(
% 0.22/0.38    ( ! [X0 : $i] : (($true != vAPP($o,$o,vAPP($i,sTfun($o,$o),says,X0),$true)) | (vAPP($i,$o,knave,X0) != $true)) )),
% 0.22/0.38    inference(equality_resolution,[],[f31])).
% 0.22/0.38  thf(f31,plain,(
% 0.22/0.38    ( ! [X0 : $i,X1 : $o] : (($true != X1) | (vAPP($o,$o,vAPP($i,sTfun($o,$o),says,X0),X1) != $true) | (vAPP($i,$o,knave,X0) != $true)) )),
% 0.22/0.38    inference(cnf_transformation,[],[f27])).
% 0.22/0.38  thf(f27,plain,(
% 0.22/0.38    ! [X0,X1 : $o] : (($true != X1) | (vAPP($o,$o,vAPP($i,sTfun($o,$o),says,X0),X1) != $true) | (vAPP($i,$o,knave,X0) != $true))),
% 0.22/0.38    inference(flattening,[],[f26])).
% 0.22/0.38  thf(f26,plain,(
% 0.22/0.38    ! [X0,X1 : $o] : (($true != X1) | ((vAPP($o,$o,vAPP($i,sTfun($o,$o),says,X0),X1) != $true) | (vAPP($i,$o,knave,X0) != $true)))),
% 0.22/0.38    inference(ennf_transformation,[],[f22])).
% 0.22/0.38  thf(f22,plain,(
% 0.22/0.38    ! [X0,X1 : $o] : (((vAPP($o,$o,vAPP($i,sTfun($o,$o),says,X0),X1) = $true) & (vAPP($i,$o,knave,X0) = $true)) => ($true != X1))),
% 0.22/0.38    inference(flattening,[],[f17])).
% 0.22/0.38  thf(f17,plain,(
% 0.22/0.38    ! [X0,X1 : $o] : (((vAPP($o,$o,vAPP($i,sTfun($o,$o),says,X0),X1) = $true) & (vAPP($i,$o,knave,X0) = $true)) => ~($true = X1))),
% 0.22/0.38    inference(fool_elimination,[],[f16])).
% 0.22/0.38  thf(f16,plain,(
% 0.22/0.38    ! [X0,X1 : $o] : ((vAPP($o,$o,vAPP($i,sTfun($o,$o),says,X0),X1) & vAPP($i,$o,knave,X0)) => ~X1)),
% 0.22/0.38    inference(rectify,[],[f3])).
% 0.22/0.38  thf(f3,axiom,(
% 0.22/0.38    ! [X0,X1 : $o] : ((vAPP($o,$o,vAPP($i,sTfun($o,$o),says,X0),X1) & vAPP($i,$o,knave,X0)) => ~X1)),
% 0.22/0.38    file('/export/starexec/sandbox/benchmark/theBenchmark.p',knaves_lie)).
% 0.22/0.38  thf(f87,plain,(
% 0.22/0.38    ~spl0_2),
% 0.22/0.38    inference(avatar_contradiction_clause,[],[f86])).
% 0.22/0.38  thf(f86,plain,(
% 0.22/0.38    $false | ~spl0_2),
% 0.22/0.38    inference(trivial_inequality_removal,[],[f83])).
% 0.22/0.38  thf(f83,plain,(
% 0.22/0.38    ($true != $true) | ($true = $false) | ~spl0_2),
% 0.22/0.38    inference(superposition,[],[f82,f79])).
% 0.22/0.38  thf(f79,plain,(
% 0.22/0.38    ($true = vAPP($o,$o,vAPP($i,sTfun($o,$o),says,zoey),$false)) | ~spl0_2),
% 0.22/0.38    inference(forward_demodulation,[],[f32,f73])).
% 0.22/0.38  thf(f73,plain,(
% 0.22/0.38    ( ! [X0 : $i] : ((vAPP($i,$o,knave,X0) = $false)) ) | ~spl0_2),
% 0.22/0.38    inference(trivial_inequality_removal,[],[f72])).
% 0.22/0.38  thf(f72,plain,(
% 0.22/0.38    ( ! [X0 : $i] : (($true != $true) | (vAPP($i,$o,knave,X0) = $false)) ) | ~spl0_2),
% 0.22/0.38    inference(superposition,[],[f70,f9])).
% 0.22/0.38  thf(f70,plain,(
% 0.22/0.38    ( ! [X1 : $i] : (($true != vAPP($i,$o,knave,X1))) ) | ~spl0_2),
% 0.22/0.38    inference(avatar_component_clause,[],[f69])).
% 0.22/0.38  thf(f69,plain,(
% 0.22/0.38    spl0_2 <=> ! [X1] : ($true != vAPP($i,$o,knave,X1))),
% 0.22/0.38    introduced(avatar_definition,[new_symbols(naming,[spl0_2])])).
% 0.22/0.38  thf(f82,plain,(
% 0.22/0.38    ( ! [X0 : $i,X1 : $o] : ((vAPP($o,$o,vAPP($i,sTfun($o,$o),says,X0),X1) != $true) | ($true = X1)) ) | ~spl0_2),
% 0.22/0.38    inference(trivial_inequality_removal,[],[f81])).
% 0.22/0.38  thf(f81,plain,(
% 0.22/0.38    ( ! [X0 : $i,X1 : $o] : (($true != $true) | ($true = X1) | (vAPP($o,$o,vAPP($i,sTfun($o,$o),says,X0),X1) != $true)) ) | ~spl0_2),
% 0.22/0.38    inference(forward_demodulation,[],[f30,f78])).
% 0.22/0.38  thf(f78,plain,(
% 0.22/0.38    ( ! [X0 : $i] : ((vAPP($i,$o,knight,X0) = $true)) ) | ~spl0_2),
% 0.22/0.38    inference(trivial_inequality_removal,[],[f77])).
% 0.22/0.38  thf(f77,plain,(
% 0.22/0.38    ( ! [X0 : $i] : (($true = $false) | (vAPP($i,$o,knight,X0) = $true)) ) | ~spl0_2),
% 0.22/0.38    inference(forward_demodulation,[],[f35,f73])).
% 0.22/0.38  thf(f30,plain,(
% 0.22/0.38    ( ! [X0 : $i,X1 : $o] : (($true = X1) | (vAPP($o,$o,vAPP($i,sTfun($o,$o),says,X0),X1) != $true) | (vAPP($i,$o,knight,X0) != $true)) )),
% 0.22/0.38    inference(cnf_transformation,[],[f25])).
% 0.22/0.38  thf(f25,plain,(
% 0.22/0.38    ! [X0,X1 : $o] : (($true = X1) | (vAPP($o,$o,vAPP($i,sTfun($o,$o),says,X0),X1) != $true) | (vAPP($i,$o,knight,X0) != $true))),
% 0.22/0.38    inference(flattening,[],[f24])).
% 0.22/0.38  thf(f24,plain,(
% 0.22/0.38    ! [X0,X1 : $o] : (($true = X1) | ((vAPP($o,$o,vAPP($i,sTfun($o,$o),says,X0),X1) != $true) | (vAPP($i,$o,knight,X0) != $true)))),
% 0.22/0.38    inference(ennf_transformation,[],[f15])).
% 0.22/0.38  thf(f15,plain,(
% 0.22/0.38    ! [X0,X1 : $o] : (((vAPP($o,$o,vAPP($i,sTfun($o,$o),says,X0),X1) = $true) & (vAPP($i,$o,knight,X0) = $true)) => ($true = X1))),
% 0.22/0.38    inference(fool_elimination,[],[f14])).
% 0.22/0.38  thf(f14,plain,(
% 0.22/0.38    ! [X0,X1 : $o] : ((vAPP($o,$o,vAPP($i,sTfun($o,$o),says,X0),X1) & vAPP($i,$o,knight,X0)) => X1)),
% 0.22/0.38    inference(rectify,[],[f2])).
% 0.22/0.38  thf(f2,axiom,(
% 0.22/0.38    ! [X0,X1 : $o] : ((vAPP($o,$o,vAPP($i,sTfun($o,$o),says,X0),X1) & vAPP($i,$o,knight,X0)) => X1)),
% 0.22/0.38    file('/export/starexec/sandbox/benchmark/theBenchmark.p',knights_tell_truth)).
% 0.22/0.38  thf(f71,plain,(
% 0.22/0.38    spl0_1 | spl0_2),
% 0.22/0.38    inference(avatar_split_clause,[],[f28,f69,f66])).
% 0.22/0.38  thf(f28,plain,(
% 0.22/0.38    ( ! [X0 : $i,X1 : $i] : (($true != vAPP($i,$o,knave,X1)) | (vAPP($i,$o,knight,X0) != $true)) )),
% 0.22/0.38    inference(cnf_transformation,[],[f23])).
% 0.22/0.38  thf(f23,plain,(
% 0.22/0.38    ! [X0,X1] : (($true != vAPP($i,$o,knave,X1)) | (vAPP($i,$o,knight,X0) != $true))),
% 0.22/0.38    inference(ennf_transformation,[],[f11])).
% 0.22/0.38  thf(f11,plain,(
% 0.22/0.38    ~? [X0,X1] : (($true = vAPP($i,$o,knave,X1)) & (vAPP($i,$o,knight,X0) = $true))),
% 0.22/0.38    inference(fool_elimination,[],[f10])).
% 0.22/0.38  thf(f10,plain,(
% 0.22/0.38    ~? [X0,X1] : (vAPP($i,$o,knave,X1) & vAPP($i,$o,knight,X0))),
% 0.22/0.38    inference(rectify,[],[f7])).
% 0.22/0.38  thf(f7,negated_conjecture,(
% 0.22/0.38    ~? [X2,X3] : (vAPP($i,$o,knave,X3) & vAPP($i,$o,knight,X2))),
% 0.22/0.38    inference(negated_conjecture,[],[f6])).
% 0.22/0.38  thf(f6,conjecture,(
% 0.22/0.38    ? [X2,X3] : (vAPP($i,$o,knave,X3) & vAPP($i,$o,knight,X2))),
% 0.22/0.38    file('/export/starexec/sandbox/benchmark/theBenchmark.p',who_is_knight_and_knave)).
% 0.22/0.38  % SZS output end Proof for theBenchmark
% 0.22/0.38  % (30609)------------------------------
% 0.22/0.38  % (30609)Version: Vampire 4.8 (commit 3a798227e on 2024-05-03 07:42:47 +0200)
% 0.22/0.38  % (30609)Termination reason: Refutation
% 0.22/0.38  
% 0.22/0.38  % (30609)Memory used [KB]: 780
% 0.22/0.38  % (30609)Time elapsed: 0.007 s
% 0.22/0.38  % (30609)Instructions burned: 8 (million)
% 0.22/0.38  % (30605)Success in time 0.022 s
%------------------------------------------------------------------------------